python - Keras LSTM 多类分类

Question

我有这段适用于二进制分类的代码。我已经针对 keras imdb 数据集对其进行了测试。

    model = Sequential()
    model.add(Embedding(5000, 32, input_length=500))
    model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])        
    print(model.summary())
    model.fit(X_train, y_train, epochs=3, batch_size=64)
    # Final evaluation of the model
    scores = model.evaluate(X_test, y_test, verbose=0)

我需要将上面的代码转换为多类分类，总共有 7 个类别。阅读几篇文章后我的理解是转换上面的代码我必须更改

model.add(Dense(7, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])  

显然改变两行以上是行不通的。我还需要更改什么才能使代码适用于多类分类。此外，我认为我必须将类更改为一种热编码，但不知道如何在 keras 中进行。

Answer 1

是的，您需要一个热门目标，您可以使用to_categorical 来编码您的目标或一种简短的方式:

model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

完整代码如下:

from keras.models import Sequential
from keras.layers import *

model = Sequential()
model.add(Embedding(5000, 32, input_length=500))
model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(7, activation='softmax'))
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.summary()

总结

Using TensorFlow backend.
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding_1 (Embedding)      (None, 500, 32)           160000    
_________________________________________________________________
lstm_1 (LSTM)                (None, 100)               53200     
_________________________________________________________________
dense_1 (Dense)              (None, 7)                 707       
=================================================================
Total params: 213,907
Trainable params: 213,907
Non-trainable params: 0
_________________________________________________________________